Contrastive ecoacoustic indices: Large-scale global soundscape characterization with contrastive inference
Abstract
Ecoacoustics mainly aims at monitoring soundscapes by means of non-invasive protocols. Despite the widespread adoption of machine and deep learning techniques, existing ecoacoustic models predominantly rely on supervised learning and, consequently, face two primary limitations: (1) the necessity of annotated data; and (2) the restriction to fixed pre-defined classes. In this work, we leverage recent advances in contrastive language-audio pretraining (CLAP) and envision its first application to large-scale soundscape analysis. As trained on extensive datasets of paired audio and global text descriptions using contrastive learning, CLAP allows computing similarity scores between audio and text prompts without the constraints of pre-defined categorical lists. This flexibility enables a comprehensive investigation of various elements within the recordings from coarse-grained (e.g. mammals, weather, humans, vehicles) to fine-grained (e.g. dog, rain, speech, airplane) descriptions. Here, we first conducted a preliminary experiment on a calibration dataset, featuring audio events likely to occur in soundscapes, which is shared with the community and constituted from an online, free sound library. Then, we developed a methodology to define reproducible, bounded, independent and interpretable Contrastive Ecoacoustic Indices (CEI), which can characterize the prevalence of four primary sound categories in soundscapes-biophony, geophony, anthropophony and technophony. We finally computed these new CEI on 9-month field recordings (189,137 1-min excerpts) monitoring both tropical (Ecuador) and temperate (France) soundscapes, portraying an anthropic gradient from protected forests to urban city centres. This experiment reveals clear soundscape patterns associated with human population density, suggesting that the CEI could be used in other ecological contexts.
Related
- CLIVeg: Contrastive Image-Vegetation Alignment for Botany-Aware Earth Observation Representations
- Understanding Perturbed Parameter Ensemble Sensitivities Using A Contrastive Learning Approach
- A field observation method to characterize site soundscape and improve detection probability estimation for eastern bat species in North America
- Bridging soil resistome and clinical inference: A four-tier evidentiary framework
- Bridging forest inventory gaps in remote and inaccessible temperate mountain forests using AlphaEarth embeddings and model-based inference
BibTeX
@article{teytaut2026contrastive,
title = {{Contrastive ecoacoustic indices: Large-scale global soundscape characterization with contrastive inference}},
author = {Yann Teytaut and Sylvain Haupert and Lorenzo Dubois and Ludovic Crochard and Frédéric Azémar and Ángel G Guevara and Patricia Balaresque and Jérôme Sueur},
journal = {Methods in Ecology and Evolution},
year = {2026},
month = oct,
doi = {10.1111/2041-210x.70369},
url = {https://hal.science/hal-05846011v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Contrastive ecoacoustic indices: Large-scale global soundscape characterization with contrastive inference
AU - Yann Teytaut
AU - Sylvain Haupert
AU - Lorenzo Dubois
AU - Ludovic Crochard
AU - Frédéric Azémar
AU - Ángel G Guevara
AU - Patricia Balaresque
AU - Jérôme Sueur
PY - 2026
DA - 2026/10/30
JO - Methods in Ecology and Evolution
DO - 10.1111/2041-210x.70369
UR - https://hal.science/hal-05846011v1
AB - Ecoacoustics mainly aims at monitoring soundscapes by means of non-invasive protocols. Despite the widespread adoption of machine and deep learning techniques, existing ecoacoustic models predominantly rely on supervised learning and, consequently, face two primary limitations: (1) the necessity of annotated data; and (2) the restriction to fixed pre-defined classes. In this work, we leverage recent advances in contrastive language-audio pretraining (CLAP) and envision its first application to large-scale soundscape analysis. As trained on extensive datasets of paired audio and global text descriptions using contrastive learning, CLAP allows computing similarity scores between audio and text prompts without the constraints of pre-defined categorical lists. This flexibility enables a comprehensive investigation of various elements within the recordings from coarse-grained (e.g. mammals, weather, humans, vehicles) to fine-grained (e.g. dog, rain, speech, airplane) descriptions. Here, we first conducted a preliminary experiment on a calibration dataset, featuring audio events likely to occur in soundscapes, which is shared with the community and constituted from an online, free sound library. Then, we developed a methodology to define reproducible, bounded, independent and interpretable Contrastive Ecoacoustic Indices (CEI), which can characterize the prevalence of four primary sound categories in soundscapes-biophony, geophony, anthropophony and technophony. We finally computed these new CEI on 9-month field recordings (189,137 1-min excerpts) monitoring both tropical (Ecuador) and temperate (France) soundscapes, portraying an anthropic gradient from protected forests to urban city centres. This experiment reveals clear soundscape patterns associated with human population density, suggesting that the CEI could be used in other ecological contexts.
SN - 2041-210X
SN - 2041-210X
ER -